Features
Model-agnostic Generators for LLM output generation
Action classes for defining reusable AI-driven tasks
Agent abstraction with automatic action selection
Custom Generator Output Adapters for flexible responses
Agent Triggers for initiating workflows
Built-in support for streaming responses
Integration with Ollama for local LLM execution
Integration with llamafile for local inference
Voice chat capabilities via Rails integration
TDD bot builder using Sublayer components
Dynamic output structure handling
Configurable model providers (OpenAI, Anthropic)
Laguna XS.2 model (33B params, 3B active, on-device)
Laguna M.1 model (225B params, 23B active, via API)
256K context length for multi-step reasoning
Multi-agent orchestration with planning and tool use
Sandboxed agent execution environments
Developer surfaces: agents, TUI, IDE extensions, binaries
Custom foundation models deployed on-prem or in VPC
Data connectors to repos, databases, data warehouses
Role-based access control for humans and agents
Executive-grade governance and auditability
On-prem, VPC, and workstation deployment (defense only)
Forward Deployed Research Engineers embed with teams
Real-time observability with end-to-end traces
Air-gapped network support
Open-weight model weights available
